mindroom-ai/mindroom

mindroom-docs

MindRoom documentation corpus for accurate product, configuration, and workflow guidance.

Langue du texte source : anglais

docs-review

Review documentation for accuracy, completeness, and consistency against the actual codebase.

Langue du texte source : anglais

agent-cli-dev

Spawns AI coding agents in isolated git worktrees. Use when the user asks to spawn or launch an agent, delegate a task to a separate agent, work in a separate worktree, or parallelize development across features.

Langue du texte source : anglais

agent-cli-tmux-supervision

Use when spawning and supervising multiple agent-cli Codex worktrees through tmux, especially when you must poll progress, force prompt rereads against the local TASK file, run current-context and fresh-context pr-review loops, and verify that review fixes…

Langue du texte source : anglais

live-test

Run live end-to-end checks for this repository. Use when booting the local MindRoom stack or SaaS sandbox, starting an isolated local Matrix/backend instance, creating disposable Matrix accounts, sending or reading messages with Matty, hitting live API…

Langue du texte source : anglais

native-subagent-pr-loop

Use when the user asks for native Codex sub-agents, parallel PR review agents, unbiased re-review loops, or main-thread fixes after agent findings in the MindRoom repository.

Langue du texte source : anglais

address-pr-review-comments

Use when fetching, triaging, or addressing PR review comments from GitHub, copied text, cloud AI reviewers, or other coding agents in the MindRoom repository.

Langue du texte source : anglais

code-debate

Two coding agents debate code changes through a shared DEBATE.md file. Use when you want adversarial review of a commit, diff, or PR.

Langue du texte source : anglais

pr-review

Zero-tolerance pull request review. Every issue is a blocker. Use when reviewing PRs for merge readiness.

Langue du texte source : anglais

duplication-audit

Find duplicated functionality across the codebase and propose minimal, safe generalizations.

Langue du texte source : anglais